Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.8060. Min Act: -0.1700
Data Index: 8609541 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.6185. Min Act: -0.1700
Data Index: 7532769 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.5560. Min Act: -0.1700
Data Index: 3043883 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.5560. Min Act: -0.1700
Data Index: 2551846 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.5560. Min Act: -0.1700
Data Index: 8083977 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.5560. Min Act: -0.1700
Data Index: 3867779 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.3685. Min Act: -0.1700
Data Index: 7327007 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.3060. Min Act: -0.1700
Data Index: 8310858 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.2435. Min Act: -0.1700
Data Index: 4742078 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.2435. Min Act: -0.1700
Data Index: 2648781 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.1810. Min Act: -0.1700
Data Index: 5705427 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.1810. Min Act: -0.1700
Data Index: 537037 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.1810. Min Act: -0.1700
Data Index: 6982365 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.2122. Min Act: -0.1700
Data Index: 3464818 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.1497. Min Act: -0.1700
Data Index: 4887659 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.0560. Min Act: -0.1700
Data Index: 3646915 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.0872. Min Act: -0.1700
Data Index: 2363620 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.0872. Min Act: -0.1700
Data Index: 1711468 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.0560. Min Act: -0.1700
Data Index: 3533545 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8060. Min Range: -8.8060
Max Act: 8.0247. Min Act: -0.1700
Data Index: 7035448 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19